[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1310961884-11634-2-git-send-email-david@fromorbit.com>
Date: Mon, 18 Jul 2011 14:04:43 +1000
From: Dave Chinner <david@...morbit.com>
To: linux-fsdevel@...r.kernel.org
Cc: linux-kernel@...r.kernel.org, xfs@....sgi.com
Subject: [PATCH 1/2] vfs: split generic splice code from i_mutex locking
From: Dave Chinner <dchinner@...hat.com>
XFS holds locks that should be nested inside the inode->i_mutex when
generic_file_splice_write is called. This function takes the
i_mutex, and so we get a lock inversion that triggers lockdep
warnings and has been found to cause real deadlocks.
XFS does not need the splice code to take the i_mutex to do the page
cache manipulation, so add a new function
generic_file_splice_write_unlocked() that avoids the locking of the
i_mutex for XFS to call.
Signed-off-by: Dave Chinner <dchinner@...hat.com>
---
fs/splice.c | 39 +++++++++++++++++++++++++++++++++++----
include/linux/fs.h | 2 ++
2 files changed, 37 insertions(+), 4 deletions(-)
diff --git a/fs/splice.c b/fs/splice.c
index aa866d3..c15137d 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -980,8 +980,9 @@ ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out,
*
*/
ssize_t
-generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
- loff_t *ppos, size_t len, unsigned int flags)
+__generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
+ loff_t *ppos, size_t len, unsigned int flags,
+ int need_imutex)
{
struct address_space *mapping = out->f_mapping;
struct inode *inode = mapping->host;
@@ -1001,13 +1002,15 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
if (ret <= 0)
break;
- mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
+ if (need_imutex)
+ mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
ret = file_remove_suid(out);
if (!ret) {
file_update_time(out);
ret = splice_from_pipe_feed(pipe, &sd, pipe_to_file);
}
- mutex_unlock(&inode->i_mutex);
+ if (need_imutex)
+ mutex_unlock(&inode->i_mutex);
} while (ret > 0);
splice_from_pipe_end(pipe, &sd);
@@ -1033,8 +1036,36 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
return ret;
}
+/**
+ * generic_file_splice_write - splice data from a pipe to a file
+ * @pipe: pipe info
+ * @out: file to write to
+ * @ppos: position in @out
+ * @len: number of bytes to splice
+ * @flags: splice modifier flags
+ *
+ * Description:
+ * Will either move or copy pages (determined by @flags options) from
+ * the given pipe inode to the given file.
+ *
+ */
+ssize_t
+generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
+ loff_t *ppos, size_t len, unsigned int flags)
+{
+ return __generic_file_splice_write(pipe, out, ppos, len, flags, 1);
+}
EXPORT_SYMBOL(generic_file_splice_write);
+ssize_t
+generic_file_splice_write_unlocked(struct pipe_inode_info *pipe,
+ struct file *out, loff_t *ppos,
+ size_t len, unsigned int flags)
+{
+ return __generic_file_splice_write(pipe, out, ppos, len, flags, 0);
+}
+EXPORT_SYMBOL(generic_file_splice_write_unlocked);
+
static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
struct splice_desc *sd)
{
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 54c49e5..3a8b984 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2368,6 +2368,8 @@ extern ssize_t default_file_splice_read(struct file *, loff_t *,
struct pipe_inode_info *, size_t, unsigned int);
extern ssize_t generic_file_splice_write(struct pipe_inode_info *,
struct file *, loff_t *, size_t, unsigned int);
+extern ssize_t generic_file_splice_write_unlocked(struct pipe_inode_info *,
+ struct file *, loff_t *, size_t, unsigned int);
extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
struct file *out, loff_t *, size_t len, unsigned int flags);
extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
--
1.7.5.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists